Re: range-based cache flushing (was Re: Linux 2.6.29)

[James Bottomley <James.Bottomley@HansenPartnership.com>]

On Tue, 2009-03-31 at 21:28 -0400, Jeff Garzik wrote:
> James Bottomley wrote:
> > On Mon, 2009-03-30 at 15:05 -0400, Jeff Garzik wrote:
> >> James Bottomley wrote:
> >>> On Wed, 2009-03-25 at 16:25 -0400, Ric Wheeler wrote:
> >>>> Jeff Garzik wrote:
> >>>>> Ric Wheeler wrote:> And, as I am sure that you do know, to add insult 
> >>>>> to injury, FLUSH_CACHE
> >>>>>> is per device (not file system).
> >>>>>> When you issue an fsync() on a disk with multiple partitions, you 
> >>>>>> will flush the data for all of its partitions from the write cache....
> >>>>> SCSI'S SYNCHRONIZE CACHE command already accepts an (LBA, length) 
> >>>>> pair.  We could make use of that.
> >>>>> And I bet we could convince T13 to add FLUSH CACHE RANGE, if we could 
> >>>>> demonstrate clear benefit.
> >>>> How well supported is this in SCSI?  Can we try it out with a commodity 
> >>>> SAS drive?
> >>> What do you mean by well supported?  The way the SCSI standard is
> >>> written, a device can do a complete cache flush when a range flush is
> >>> requested and still be fully standards compliant.  There's no easy way
> >>> to tell if it does a complete cache flush every time other than by
> >>> taking the firmware apart (or asking the manufacturer).
> >> Quite true, though wondering aloud...
> >>
> >> How difficult would it be to pass the "lower-bound" LBA to SYNCHRONIZE 
> >> CACHE, where "lower bound" is defined as the lowest sector in the range 
> >> of sectors to be flushed?
> > 
> > Actually, the implementation is designed to allow this.  The standard
> > says if the number of blocks is zero that means flush from the specified
> > LBA to the end of the device.  The sync cache we currently use has LBA 0
> > and number of blocks zero (which means flush everything).
> 
> Yeah, that feature of the spec was what got me thinking.
> 
> "difficult" was referring more to the kernel side of things...  if 
> calculating the lowest LBA of a write barrier is difficult and/or 
> CPU-consuming, the effort may not be worth it.
> 
> But if we could stick a
> 
> 	if (LBA < barrier-lower-bound)
> 		barrier-lower-bound = LBA
> 
> somewhere, then pass that to SYNCHRONIZE CACHE, it could be a cheap way 
> to increase sync-cache speed.
> 
> It seems extremely unlikely that sync-cache speed would _decrease_:  for 
> flush-everything firmwares, the sync-cache speed would remain unchanged.

It's not impossible, though ... since the drive fw processor is probably
pretty slow, but yes, it should hopefully be as fast or faster than full
sync cache.

> >> That seems like a reasonable optimization -- it gives the drive an easy 
> >> way to skip sync'ing sectors lower than the lower-bound LBA, if it is 
> >> capable.  Otherwise, a standards-compliant firmware will behave as you 
> >> describe, and do what our code currently expects today -- a full cache 
> >> flush.
> >>
> >> This seems like a good way to speed up cache flush [on SCSI], while also 
> >> perhaps experimenting with a more fine-grained way to pass down write 
> >> barriers to the device.
> >>
> >> Not a high priority thing overall, but OTOH, consider the case of 
> >> placing your journal at the end of the disk.  You could then issue a 
> >> cache flush with a non-zero starting offset:
> >>
> >> 	SYNCHRONIZE CACHE (max sectors - JOURNAL_SIZE, ~0)
> >>
> >> That should be trivial even for dumb disk firmwares to optimize.
> > 
> > We could try it ... I'm still not sure how we'd tell the device is
> > actually implementing it and not flushing the entire device.
> 
> Is that knowledge necessary?
> 
> Assuming the lower-bound is super-cheap to calculate, then the two most 
> likely outcomes are:  sync-cache speed remains the same, or sync-cache 
> speed increases.

Yes, agreed ... we might as well tell the FW if it's cheap to know
whether or not it acts on it.

> If the calculation of lower-bound is costly, I could see the need for 
> that knowledge -- but if the cost is too high, the entire effort it 
> likely to be scuttled, rather than worrying about detecting 
> flush-everything firmwares.

I really think, though, it's time to look again at how we implement
barriers.  Even properly implemented range flushing (if we can do it) is
only decreasing the amount of overhead in a flush barrier.

If we could make the filesystems tolerant or at least aware that there
might be very rare periods during operation when barriers get violated
(during error processing or queue full handling) we could look again at
implementing barriers via ordered tags.

James